Senior HPC Engineer: GPU Clusters & MPI Scaling

Frontdoor Defense; Palo Alto (CA); On-site; USD 180,000 - 250,000; Full time

Job summary

PsiQuantum seeks an experienced Sr. HPC Engineer to design, develop, and optimize HPC software that leverages NVIDIA GPUs, AMD CPUs, and MPI for distributed computing. You will advance scalable HPC clusters and high-performance applications across multi-node environments.

Applicants should have 3+ years in HPC development, 5+ years in scientific software, and strong CUDA/MPI/OpenMP skills. The role is based in Palo Alto, CA, and involves cross-team collaboration and thorough documentation of

Qualifications

• Bachelor's or master's in CS, EE, Computational Science, or related field.
• 3+ years HPC development focusing on parallel and distributed computing; 5+ years in scientific software development.
• Proficiency in CUDA and NVIDIA HPC software stack (cuDNN, NCCL, TensorRT).
• Parallel programming with MPI, OpenMP, and related paradigms.
• Strong ability to scale clusters and optimize distributed software.
• Languages: C/C++, Python; Ansible/Terraform/Packer.

Responsibilities

• Develop and optimize HPC software leveraging NVIDIA GPUs and AMD CPUs.
• Apply MPI, CUDA, OpenMP to scale apps on multi-core and multi-GPU systems.
• Design, deploy, and scale HPC nodes to match data and compute demands.
• Identify GPU/CPU algorithms for scalable performance.
• Profile and benchmark HPC apps using Nsight, μProf, and VTune.
• Collaborate with scientists, engineers, and IT to optimize deployments.
• Document code and scaling processes; report performance metrics.

Skills

CUDA

MPI

OpenMP

Python

C/C++

Communication

Education

Bachelor's or master's in CS/EE/Computational Science

Tools

NVIDIA Nsight

AMD μProf

Intel VTune

cuDNN

NCCL

TensorRT

Docker

Singularity

Ansible

Terraform

Packer

Job description

PsiQuantum seeks an experienced Sr. HPC Engineer to design, develop, and optimize HPC software that leverages NVIDIA GPUs, AMD CPUs, and MPI for distributed computing. You will advance scalable HPC clusters and high-performance applications across multi-node environments.

Applicants should have 3+ years in HPC development, 5+ years in scientific software, and strong CUDA/MPI/OpenMP skills. The role is based in Palo Alto, CA, and involves cross-team collaboration and thorough documentation of